Data Cleansing for AI & ML

About the Course:

Machine Learning is highly dependent on adequate data. Not only does quantity matter, but more importantly, quality. In this session, we’ll cover how to build a custom automated process using various tools like Excel, Databricks, and SQL. We’ll explore methods and strategies for handling missing data, identifying which data to use in the ML lifecycle, and improving accuracy.

Machine learning systems are only as strong as the data they are built on, making data quality a critical factor in model performance and reliability. This course focuses on the principles and practical techniques of data cleansing for AI and ML, emphasizing why both data quantity and, more importantly, data quality directly impact outcomes. Participants will learn how to identify issues in datasets such as missing values, inconsistencies, and outliers, and understand how these challenges affect model accuracy and decision-making.

The session also demonstrates how to build automated data cleansing workflows using tools such as Excel, Databricks, and SQL. Through practical approaches, learners will explore strategies for selecting the right data for machine learning pipelines, improving dataset reliability, and supporting model retraining and evaluation. By the end of the course, participants will have a clearer understanding of how to prepare high-quality datasets that enhance performance across the full machine learning lifecycle.

Course Objectives:

• This course will teach you techniques for quickly identifying outliers, handling missing data, and the ability to identify the correct data needed for Machine learning and Artificial Intelligence.  
• In addition, we’ll identify strategies for retraining, evaluating, and procedures throughout the ML lifecycle.

Who is the target audience?

• Software Developers
• AI Engineers
• Data Analysts
• Data Engineers
• Machine Learning Engineers
• Business Intelligence Analysts
• Data Scientists
• Analytics Engineers
• Cloud Data Engineers
• ETL Developers
• Database Administrators (DBAs)
• Data Warehouse Engineers
• Data Quality Analysts
• Data Governance Specialists
• AI / ML Platform Engineers
• Applied Machine Learning Practitioners
• Statistical Analysts
• Research Analysts (Quantitative / Data-focused)
• Product Analysts working with data models
• Reporting Analysts
• Operations Analysts using data-driven systems
• Enterprise Data Architects
• Information Systems Engineers
• Junior Data Scientists transitioning into ML workflows
• BI Developers working with SQL and analytics pipelines
• Automation Engineers working with data pipelines
• Big Data Engineers working with distributed systems like Databricks
• Decision Intelligence Analysts
• Technical Consultants in Data & Analytics
• Developers working on data preprocessing pipelines for AI systems

Basic Knowledge:

• Working knowledge of Python, Databricks, and SQL